St Worker Xhigh — Security agent for Claude Code
Strikethroo task-execution worker at the XHIGH reasoning-effort tier.
How to install St Worker Xhigh
Installs to ~/.claude/agents/lullabot-sandbar-st-worker-xhigh.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/Lullabot/sandbar/HEAD/.claude/agents/st-worker-xhigh.md -o ~/.claude/agents/lullabot-sandbar-st-worker-xhigh.md Restart Claude Code, or start a new session, for it to be picked up.
What St Worker Xhigh does
name: st-worker-xhigh description: Strikethroo task-execution worker at the XHIGH reasoning-effort tier. Reserved for the hardest, highest-risk tasks — novel algorithms, architecture-defining work, concurrency, or security- and data-sensitive changes — where correctness dominates cost. Effort is fixed by this agent's frontmatter; the orchestrator overrides the model per task. model: opus effort: xhigh
You are a Strikethroo task-execution worker. An orchestrator dispatches you to impleme
Alternatives in Security
- Beads Warden — Guard the beads execution record: enforce the write-flush-verify discipline that defeats the bd rapid-write ra 2.7k ★
- API Expert — Use this agent for Output.ai API server design, Express middleware configuration, workflow execution endpoints 434 ★
- Sa Agent — AWS Solutions Architect teammate — architecture review, cost/security recommendations, Well-Architected assess 55 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Executor Opus Xhigh
Ticket executor for tickets where judgment is the work — money, capacity, stored enums, migrations with a corr
Architect Task
Ceiling-level reasoning agent for the hardest problems — architectural decisions with long-lasting consequence
Paradigm Assessor
Use this agent for a high-skepticism, 'red-team' audit of a novel 'paradigm-defining' framework. This agent's
Genius Fable
Tier-1 genius worker on Fable. Use for architecture decisions, subtle bugs, algorithm and data-model design, s
Reviewer Xhigh
Read-only code/security reviewer running Opus at xhigh effort. Used by the review rule in CLAUDE.md. Give it t
Jev Architect
Deepest-reasoning subagent for Jev-routed subtasks that need design decisions (choosing between approaches, de
Related Skills
AI Orchestration
Host-neutral AI orchestration protocol for Codex, Antigravity/Gemini, OmniRoute, and ESRA, defining agent role
Codex Skill
by klaudworks - Enables users to prompt codex from claude code. Unlike the raw codex mcp server, this skill in
Codex Consult
Consult OpenAI Codex (codex exec) for a second opinion on a prompt. Handles the argv-hang, stdin-mode, reasoni